Python爬虫--爬取哔哩哔哩（B站）短视频平台视频

企业开发 2024-03-16 22:30:33 阅读次数: 0

目录

1、开发工具

2、第三方库

3、实现思路

4.单个爬取B站视频

5.批量爬取B站视频

6.查找所需数据

结尾    

1、开发工具

Python3.9

pycharm

扫描二维码关注公众号，回复： 17381432 查看本文章

requests

和其他python内置库

2、第三方库

安装第三方库

pip install requests

3、实现思路

1.用requests发送get请求，获得下载链接

2.将下载到B站视频和音频保存到本地

3.使用ffmpeg来合并视频和音频。

4.并保存到本地。

4.单个爬取B站视频
import os
import requests
import json
import re
from bs4 import BeautifulSoup
import subprocess
from detail_video import video_bvid

# video_bvid 是一个从外部得到的单个视频ID
video_bvid = 'your-single-bvid'


class BilibiliVideoAudio:
    def __init__(self, bvid):
        self.bvid = bvid
        self.headers = {
            "referer": "https://search.bilibili.com/all?keyword=%E4%B8%BB%E6%92%AD%E8%AF%B4%E8%81%94%E6%92%AD&from_source=webtop_search&spm_id_from=333.1007&search_source=5&page=4&o=90",
            "origin": "https://search.bilibili.com",
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0',
            'Accept-Encoding': 'gzip, deflate, br'
        }

    def get_video_audio(self):
        # 构造视频链接并发送请求获取页面内容
        url = f'https://www.bilibili.com/video/{self.bvid}/?spm_id_from=333.337.search-card.all.click&vd_source=14378ecd144bed421affe1fe0ddd8981'
        content = requests.get(url, headers=self.headers).content.decode('utf-8')
        soup = BeautifulSoup(content, 'html.parser')

        # 获取视频标题
        meta_tag = soup.head.find('meta', attrs={'name': 'title'})
        title = meta_tag['content']

        # 获取视频和音频链接
        pattern = r'window\.__playinfo__=({.*?})\s*</script>'
        json_data = re.findall(pattern, content)[0]
        data = json.loads(json_data)

        video_url = data['data']['dash']['video'][0]['base_url']
        audio_url = data['data']['dash']['audio'][0]['base_url']

        return {
            'title': title,
            'video_url': video_url,
            'audio_url': audio_url
        }

    def download_video_audio(self, url, filename):
        # 对文件名进行清理，去除不合规字符
        filename = self.sanitize_filename(filename)
        try:
            # 发送请求下载视频或音频文件
            resp = requests.get(url, headers=self.headers).content
            download_path = os.path.join('D:\\video', filename)  # 构造下载路径
            with open(download_path, mode='wb') as file:
                file.write(resp)
            print("{:*^30}".format(f"下载完成：{filename}"))
        except Exception as e:
            print(e)

    def sanitize_filename(self, filename):
        # 定义不合规字符的正则表达式
        invalid_chars_regex = r'[\"*<>?\\|/:,]'

        # 替换不合规字符为空格
        sanitized_filename = re.sub(invalid_chars_regex, ' ', filename)

        return sanitized_filename

    def merge_video_audio(self, video_path, audio_path, output_path):
        """
        使用ffmpeg来合并视频和音频。
        """
        try:
            command = [
                'ffmpeg',
                '-y',  # 覆盖输出文件如果它已经存在
                '-i', video_path,  # 输入视频路径
                '-i', audio_path,  # 输入音频路径
                '-c', 'copy',  # 复制原始数据，不进行转码
                output_path  # 输出视频路径
            ]
            subprocess.run(command, check=True)
            print(f"视频和音频合并完成：{output_path}")
        except subprocess.CalledProcessError as e:
            print(f"合并失败: {e}")


def main():
   try:
        # 只处理一个 bvid
        bilibili = BilibiliVideoAudio(video_bvid)
        video_audio_info = bilibili.get_video_audio()
        
        title = video_audio_info['title']
        video_url = video_audio_info['video_url']
        audio_url = video_audio_info['audio_url']
        
        processed_videos_path = 'D:\\processed_videos'
        if not os.path.exists(processed_videos_path):
            os.makedirs(processed_videos_path)
        
        video_filename = f"{title}.mp4"
        audio_filename = f"{title}.mp3"
        output_filename = f"{title} - combined.mp4"
        
        video_file_path = os.path.join('D:\\video', video_filename)
        audio_file_path = os.path.join('D:\\video', audio_filename)
        output_file_path = os.path.join(processed_videos_path, output_filename)
        
        bilibili.download_video_audio(video_url, video_filename)  # 下载视频
        bilibili.download_video_audio(audio_url, audio_filename)  # 下载音频
        bilibili.merge_video_audio(video_file_path, audio_file_path, output_file_path)  # 合并视频和音频
        
        # Optional: Delete the separate files after merge
        # os.remove(video_file_path)
        # os.remove(audio_file_path)
        
    except Exception as ex:
        print(f"Failed to process video/audio for {video_bvid}: {ex}")

main()

5.批量爬取B站视频
# 批量爬取b站上的视频
import os
import requests
import json
import re
from bs4 import BeautifulSoup
import subprocess
from detail_video import video_bvid


class BilibiliVideoAudio:
    def __init__(self, bvid):
        self.bvid = bvid
        self.headers = {
            "referer": "https://search.bilibili.com/all?keyword=%E4%B8%BB%E6%92%AD%E8%AF%B4%E8%81%94%E6%92%AD&from_source=webtop_search&spm_id_from=333.1007&search_source=5&page=4&o=90",
            "origin": "https://search.bilibili.com",
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0',
            'Accept-Encoding': 'gzip, deflate, br'
        }

    def get_video_audio(self):
        # 构造视频链接并发送请求获取页面内容
        url = f'https://www.bilibili.com/video/{self.bvid}/?spm_id_from=333.337.search-card.all.click&vd_source=14378ecd144bed421affe1fe0ddd8981'
        content = requests.get(url, headers=self.headers).content.decode('utf-8')
        soup = BeautifulSoup(content, 'html.parser')

        # 获取视频标题
        meta_tag = soup.head.find('meta', attrs={'name': 'title'})
        title = meta_tag['content']

        # 获取视频和音频链接
        pattern = r'window\.__playinfo__=({.*?})\s*</script>'
        json_data = re.findall(pattern, content)[0]
        data = json.loads(json_data)

        video_url = data['data']['dash']['video'][0]['base_url']
        audio_url = data['data']['dash']['audio'][0]['base_url']

        return {
            'title': title,
            'video_url': video_url,
            'audio_url': audio_url
        }

    def download_video_audio(self, url, filename):
        # 对文件名进行清理，去除不合规字符
        filename = self.sanitize_filename(filename)
        try:
            # 发送请求下载视频或音频文件
            resp = requests.get(url, headers=self.headers).content
            download_path = os.path.join('D:\\video', filename)  # 构造下载路径
            with open(download_path, mode='wb') as file:
                file.write(resp)
            print("{:*^30}".format(f"下载完成：{filename}"))
        except Exception as e:
            print(e)

    def sanitize_filename(self, filename):
        # 定义不合规字符的正则表达式
        invalid_chars_regex = r'[\"*<>?\\|/:,]'

        # 替换不合规字符为空格
        sanitized_filename = re.sub(invalid_chars_regex, ' ', filename)

        return sanitized_filename

    def merge_video_audio(self, video_path, audio_path, output_path):
        """
        使用ffmpeg来合并视频和音频。
        """
        try:
            command = [
                'ffmpeg',
                '-y',  # 覆盖输出文件如果它已经存在
                '-i', video_path,  # 输入视频路径
                '-i', audio_path,  # 输入音频路径
                '-c', 'copy',  # 复制原始数据，不进行转码
                output_path  # 输出视频路径
            ]
            subprocess.run(command, check=True)
            print(f"视频和音频合并完成：{output_path}")
        except subprocess.CalledProcessError as e:
            print(f"合并失败: {e}")


def main():
    # 批量获取多个视频的bid
    bvids = [
        #      0             1              2               3
        "BV187411i7zw","BV1wi4y1E7E6","BV1Gz4y1X7vh","BV1Lh411d7Lw",    # 1
        #      4             5              6               7
        "BV1mJ411D7QB","BV1Z5411w7Xb","BV1op4y167kS","BV1Mp4y1p7Ck",    # 2
        #      8             9              10              11
        "BV1nJ41187Zy","BV1qb4y1Z7JK","BV1f5411379u","BV1kt4y1Q792",    # 3
        #      12             13             14             15
        "BV1Qy4y1e7kk","BV1T7411T7q6","BV1k64y1k7QL","BV1J5411c7Rw",    # 4
        #      16             17              18            19
        "BV1Db4y1y7yL","BV1cC4y1878T","BV11y4y1z7bY","BV1LJ411S7ML",    # 5
        #      20             21              22            23
        "BV1X54y1L7mt","BV1S64y1D7HM","BV1rK4y1d7mZ","BV1b64y1y7AE",    # 6
        #      24             25              26            27
        "BV1TK411F7MU","BV1HN411f7Em","BV1QA411x7KB","BV1pM4y1K7Ao",    # 7
        #      28             29             30             31
        "BV1os4y1s7Aw","BV1sv411e71L","BV1xZ4y1A7gn","BV1E3411B7Q3",    # 8
        #      32             33              34            35
        "BV1664y1d78D","BV1xv41177MR","BV13q4y1S7y1","BV1kJ411H7y8",    # 9
        #      36             37              38            39
        "BV1Cq4y1Z7pM","BV1Jf4y147U7","BV1az4y117h4","BV1gy4y1h7wS",    # 10
        ]


    for bvid in bvids:
        try:
            bilibili = BilibiliVideoAudio(bvid)
            video_audio_info = bilibili.get_video_audio()

            title = video_audio_info['title']
            video_url = video_audio_info['video_url']
            audio_url = video_audio_info['audio_url']

            bilibili.download_video_audio(video_url, f"{title}.mp4")  # 下载视频
            bilibili.download_video_audio(audio_url, f"{title}.mp3")  # 下载音频
        except Exception as ex:
            print(f"Failed to download video/audio for {bvid}: {ex}")

    processed_videos_path = 'D:\\processed_videos'
    if not os.path.exists(processed_videos_path):
        os.makedirs(processed_videos_path)
    
    # 注意：B站和其他短视频平台的视频不同，需要分别下载视频和音频，最后将视频和音频拼接到一块
    for bvid in bvids:
        try:
            bilibili = BilibiliVideoAudio(bvid)
            video_audio_info = bilibili.get_video_audio()

            title = video_audio_info['title']
            video_url = video_audio_info['video_url']
            audio_url = video_audio_info['audio_url']

            video_filename = f"{title}.mp4"
            audio_filename = f"{title}.mp3"
            output_filename = f"{title} - combined.mp4"

            video_file_path = os.path.join('D:\\video', video_filename)
            audio_file_path = os.path.join('D:\\video', audio_filename)
            output_file_path = os.path.join(processed_videos_path, output_filename)

            bilibili.download_video_audio(video_url, video_filename)  # 下载视频
            bilibili.download_video_audio(audio_url, audio_filename)  # 下载音频
            bilibili.merge_video_audio(video_file_path, audio_file_path, output_file_path)  # 合并视频和音频

            # Optional: Delete the separate files after merge
            # os.remove(video_file_path)
            # os.remove(audio_file_path)

        except Exception as ex:
            print(f"Failed to process video/audio for {bvid}: {ex}")


main()
6.查找所需数据

   1）bvid    

   2）referer / origin / User-Agent / Accept-Encoding

   

结尾    

希望大家喜欢我的分享!!!

猜你喜欢

转载自blog.csdn.net/y2878672183/article/details/135679905
今日推荐
火速冲上 GitHub 热榜 —— 开源编程语言、框架哪有这么可爱？
北京人形机器人创新中心发布全球首个纯电驱拟人奔跑的全尺寸人形机器人“天工”
LFOSSA 源来如此公开课 | 掌握云原生未来：CNCF 认证全面攻略与备考秘籍
国产云输入法——仅华为无云端数据上传安全问题
开源日报 | 工业开源项目OGG 1.0；姐姐，你要和我一起配置火狐吗；苹果AI遥遥落后？Fedora 40
开放签电子签章：停止新增，优化体验，前进更进（五一假期前工作）
开源日报 | 中学生开源前端动画引擎；全球首个Llama3 8B中文版开源模型；联想电脑恐出局；Linus讽刺AI炒作
周排行
浏览器对同一域名进行请求的最大并发连接数
React Hook之自定义Hook
【转】MyBatis缓存机制
-Java-泛型
自动化测试常用脚本-发送邮件
LeetCode#859: Buddy Strings
java、Python处理字符串
第二篇の博客
Hadoop伪分布式环境安装
SQL Server进阶（十一）临时表、表变量
每日归档
更多
2024-04-27(56)
2024-04-26(39)
2024-04-25(22)
2024-04-24(36)
2024-04-23(26)
2024-04-22(39)
2024-04-21(0)
2024-04-20(6)
2024-04-19(5)
2024-04-18(0)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022